© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4379
    Prev
    Next
    INDEX
    Explanations

    The neuron overwhelmingly responds to occurrences of the coordinating conjunction “or.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    งาน
    1.42
     również
    1.17
    Also
    1.08
    ALSO
    0.98
    պ
    0.93
     także
    0.92
    гү
    0.90
    matic
    0.89
     Also
    0.88
    ง
    0.88
    POSITIVE LOGITS
     equivalently
    1.51
     यूँ
    1.29
    ofacial
    1.16
     вовсе
    1.11
     addirittura
    1.10
     者
    1.08
     यूं
    1.08
     eben
    1.07
    acles
    1.02
     хотя
    1.02
    Activations Density 0.373%

    No Known Activations